ML Ops Engineer, Chanakya

Highlights

• Own model lifecycle across defence and strategic sector deployments.
• Ensure AI systems stay always on, accurate, and auditable.
• Build evaluation harnesses and A/B testing for field and lab use.

Ideal candidate

An ownership-driven ML engineer with 3-5 years keeping production systems running under load. You treat uptime and correctness as non-negotiable, anticipate failures, and build trusted, auditable systems for high-stakes operational environments.

Requirements

• 3–5 years in ML engineering or MLOps with at least one production LLM or ML system in continuous operation
• Deep expertise in model serving: vLLM, TGI, Triton Inference Server, or equivalent; experience with quantised model formats (GGUF, AWQ, GPTQ)
• Experience fine-tuning and adapting models in constrained, on-prem, or air-gapped environments, including managing data pipelines and compute limitations specific to the environment
• Containerisation experience with Docker, Kubernetes, or lightweight alternatives (K3s, K0s) for constrained and edge environments; familiarity with deploying across heterogeneous hardware and infrastructure configurations
• Monitoring and observability using Prometheus, Grafana, or equivalent; ability to build custom eval dashboards
• Python fluency; familiarity with fine-tuning workflows and model evaluation frameworks
• Hands-on experience with CI/CD tooling for ML pipelines: GitHub Actions, ArgoCD, DVC, or similar